jev·agent

Concept

What is a System One model?

The name borrows from Kahneman: System Two is slow, deliberate reasoning; System One is fast, automatic judgement. Today's LLMs are all System Two. Jev is the first model built to be the other half.

The gap it fills

An autoregressive LLM answers by writing. Even when the answer is one word from a list of four, the model composes a response token by token, and you get a string that you then have to coerce back into a type your program can use. Structured-output modes and JSON schemas make that less awful, but the underlying work is unchanged: generate text, then parse it.

That is a strange way to ask which of these four queues should this ticket go to. You pay generation latency and generation pricing for a decision that is, information-theoretically, two bits.

The trade Jev makes

What it gives up

  • Free-form text generation
  • Summarising, writing, coding, conversation
  • Any answer outside the options you supply

What it gets back

  • 70–500ms end-to-end end-to-end
  • Typed values with probability distributions
  • No parsing, no retries, no schema drift
  • Calibrated confidence on every answer

“It can’t hallucinate” — carefully

This claim gets repeated loosely, so it is worth stating precisely. Jev cannot invent an option that you did not give it, cannot produce malformed output, and cannot drift off schema — the output space is exactly the set you defined. In that structural sense, hallucination is impossible.

Most systems want both

This is not a replacement for GPT, Claude or Gemini, and TypeSafe does not pitch it as one. The emerging pattern is a division of labour: Jev makes the fast decisions on the hot path — route this, classify that, is this good enough to send — and an LLM does the writing once a decision has been made. The jev-ultrafast browser agent is a clean example: Jev picks the operation and the element, and a small LLM writes text only when the operation is TYPE_TEXT.

Who built it

TypeSafe AI came out of stealth on September 15, 2026 with a $40M seed round led by DCVC. Co-founder Diogo Almeida, former OpenAI researcher and RLHF co-inventor — which is part of why a new model class from an unknown company got taken seriously on day one rather than dismissed.